EPAT Structure

Modules # Lectures* Suggested Hours​†

PRIMER NA 30

Statistics for Financial Markets 3 20

Python: Basics & Its Quant Ecosystem 2 15

Market Microstructure for Trading 3 18

Equity, FX & Futures Strategies 6 48

Data Analysis & Modeling in Python 5 30

Machine Learning for Trading 7 48

Trading Tech, Infra & Operations 2 10

Advanced Statistics for Quant Strategies 2 15

Trading & Back-testing Platforms 4 30

Portfolio Optimization & Risk Management 2 12

Options Trading & Strategies 5 35

EXAM NA NA

* Duration and number of lectures mentioned are tentative. You will be notified of the scheduled lecture a
week in advance. Includes self-study hours in addition to the lectures of about 3 hours each.

Optional Sessions

● Two preparatory sessions will be conducted before the Orientation session, one doubt solving session
on Statistics Primer and one doubt solving session on Python Primer.

● Total of four Python tutorials will be conducted after each of the first four Python lectures to answer
queries and resolve doubts on Python.

Primer

The EPAT Primer is a collection of material we have put together on the following topics.

● Introduction to Financial Markets

● Excel

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 1

● Statistics
● Python
● Options
● Machine Learning
● Matlab

Our aim in creating this is to introduce the fundamentals of specific vital ideas to students who are unfamiliar
with them. From our past experience, we have seen that students have varying degrees of understanding of
the topics mentioned above. We, therefore, recommend that you devote time to each of them accordingly (i.e.
the newer the topic is to you, the higher proportionate time you spend on it). These are the minimum required
readings for you before getting started with the EPAT lectures.

The objectives are:

● To learn about Financial Markets and get a brief understanding of how they work. You will learn about
several concepts like financial instruments, intermediaries, types of traders, investors and their roles.

● Starting from the very basics, moving on to available functions used with lots of examples to give you
full clarity and understanding of Excel.

● To understand and implement basic statistics through examples. Topics covered include
a. Data and Statistics, Difference Between Probability and Statistics, Statistics In Quant Finance &
Algorithmic Trading
b. Descriptive Statistics, Organizing and Presenting the Data, Data Types: Quantitative and Qualitative,
Frequency-Distribution of Data
c. Standard Statistical Distributions, Basics of Inferential Statistics, Covariance& Correlation, Hypothesis
Testing

● Starting from installation to using basic functions in Python with exercises in the notebook for your
complete understanding.

● To understand the basics of Options - associated terminology, options pricing basic with factors
affecting option prices and their quantification (Greeks), simple option trading strategies.

● An introduction to Machine Learning for Trading covers:

a. Supervised, Unsupervised and Reinforcement Machine Learning.
b. Different types of Machine Learning algorithms such as Linear regression, Logistic regression, K -
Nearest Neighbor, Artificial Neural Networks, Random Forest, and Support Vector Machine.
c. Application of Machine Learning in trading.

● Tutorial on MATLAB to help you understand the back-testing on MATLAB

Statistics for Financial Markets

The main tools for quantitative trading include Statistics and Excel. This module will take you through the
application of these tools and help you appreciate their importance.

The learning objectives are:

● Basics of excel, application of some trading strategies in excel. Using excel to create a back-testing model
for a given hypothesis.

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 2

● The art of visualizing data. Statistics and probability concepts (Bayesian and Frequentist methodologies),
moments of data and Central Limit Theorem.

● Applications of statistics- Random Walk Model for predicting future stock prices using simulations and
understanding results, Capital Asset Pricing Model.

● Short Introduction to Modern Portfolio Theory - statistical approximations of risk/reward.

Python: Basics & Its Quant Ecosystem

One of the key things of Algorithmic Trading is back-testing your strategy, and you need a certain level of
programming skills for the same. This module will help you understand the application of Python concepts
required for writing and back-testing your trading strategies.

The learning objectives are:

● Understanding of data types, variables, Python in-built data structures, inbuilt functions, logical
operators such as and, or, control structures: If, nested ifs, loops: for and while.

● Writing Python functions to implement the strategy.

● Introduction to some key libraries NumPy, pandas, and matplotlib.

● Installing and introduction to pandas-data reader.

● Writing and back-testing some basic strategies.

Market Microstructure for Trading

In this module, we will take you through Execution Strategies and Market Microstructure for Algorithmic
Trading.

The learning objectives are:

● Detailed understanding of ‘Orders’, ‘Pegging’, ‘Discretion Order’, ‘Blended Strategy’.

● Introduction to some key strategy ideas and other important aspects of an algo trade.

● Understanding Market Microstructure basics, order book, developing high frequency trading strategy
based on Market Microstructure theory.

● Implementing Markow model and using tick-by-tick data in your trading strategy.

Equity, FX & Futures Strategies

This module will take you through developing trading strategies across different asset classes.

The learning objectives are:

● Understanding of Equities Derivative markets, various parameters like OI, volume etc. and impact of
market players on the derivative parameters.

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 3

● VWAP strategy how to implement, effect of VWAP, how to maintain log journal.

● Basic optimization for various strategy parameters

a) Pair Trading Methodology – Identification of probable pairs, entry-exit and back-testing

b) In-depth understanding of Stationarity & co-integration
c) Position sizing and risk management

● Exposure to different types of Momentum (Time series momentum & Cross-sectional momentum).

● Trend strategy and Pair Trading strategy modeling in detail.

● ETF’s trading, including arbitrage, market making and asset allocation strategies using ETFs.

Data Analysis & Modeling in Python

The aim of this module is to help you implement your strategies in the live trading environment.

The learning objectives are:

● Learn to back-test a strategy in Python and measure the performance using Log Returns.

● Understand the basics of Object-Oriented Programming (OOP), programming layouts of various

packages, appreciate the classes over procedural programming style.

● Implement various OOP concepts in your python program - Aggregation, Inheritance, Composition,
Encapsulation, and Polymorphism.

● Back-testing methodologies & techniques for Long-Only as well as Long-Short strategies

Machine Learning for Trading

This module aims to help you implement your strategies in the live trading environment.

The learning objectives are:

● Feature Selection, Logistic Regression / Linear Discriminant Analysis /Regularisation, Decision Trees /
Ensemble methods

● Support Vector Machine, Neural Networks, Forward propagation, Backward propagation,

Hyperparameter selection, Various neural network architectures

● Building a “Principal Component Analysis” manually, conduct a pairs-trading back-test using PCA,
Simulation of multiple co-integrated assets, Sector statistical arbitrage using PCA

● Building Trading System while not overfitting, Hypothesis based strategy development, Using market
beliefs to develop hypotheses and event studies to test the hypothesis, using machine learning to help us
create, support or refute previous hypotheses, making Features Stationary and Selection, Model evaluation
and Backtesting

● Overview of Alternate Data: Sources, data formats, storage and retrieval choices, Understanding RDF
and Knowledge Graph, Tagging Unstructured Data with relevant metadata

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 4

● Using spaCy for common Text processing tasks, Understanding Topic Modeling and Topic Classification

● Understanding Machine Readable News Programmatic consumption of news

● Machine Readable News in the Financial Industry: Sample in Production use cases, Sentiment Data in
the Financial Industry: Sample in Production use cases

● Basic ideas of deep reinforcement learning such as reward, explore/exploit, Bellman equation and
memory replay.

● Challenges and problems with RL in trading, Implementation of RL in a simple strategy using

"gamification".

Trading Tech, Infra & Operations

The learning objectives are:

● To understand in detail, the System Architecture of a traditional trading system and compare it to an
automated trading system.

● To understand the need, requirements, process, advantages and applications of Algorithmic Trading.

● Understanding the infrastructure (hardware, physical, network, etc.) requirements.

● Understanding the business environment (including the regulatory environment, financials, business
insights, etc.) while setting up an Algorithmic Trading desk.

Advanced Statistics for Quant Strategies

This is an advanced module designed to take you through the application of Statistical parameters in
Quantitative Trading Strategies.

The learning objectives are:

● Study time series analysis and statistical parameters such as auto correlation function, partial auto
correlation function, maximum likelihood estimation, Akaike Information Criterion.

● Stationarity of time series, Autoregressive Process, Moving Average Process, Forecasting using ARIMA.

Trading & Back-testing Platforms

This module aims to help you understand the implementation of your strategies in the live trading
environment and will introduce you to the platform like Interactive Brokers using Python programming
language

The learning objectives are:

● Using IBridgePy API to automate your trading strategies on Interactive Brokers platform.

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 5

● Strategy Life Cycle, Manual Trading using IB Trader Workstation (TWS), Understanding IB TWS API
architecture, IB API Demo.

● Strategy flow in Blueshift Manage your portfolio in Blueshift, Demo strategies for back-testing

Portfolio Optimization & Risk Management

One of the important aspects in Algorithmic Trading is portfolio optimization and Risk management. This
module is dedicated to identifying and managing the risks involved in different kinds of strategies.

The learning objectives are:

● Different methodologies of evaluating portfolio & strategy performance. Managing a portfolio of options
instruments when more than one underlying is involved.

● Know about Risk Management structures & policies, sources of risk, risk limits & risk components
evaluation, risk control systems.

● Portfolio management & profitability analysis - Individual strategy profitability analysis: Profitability analysis
for absolute return strategies, relative return strategies, and with respect to tail risks.

● Trade sizing for an individual trading strategy using

a) Historical methodologies
b) Kelly criterion
c) Leverage space theorem

Options Trading & Strategies

One of the crucial aspects of Algorithmic Trading is portfolio optimization and Risk management. This module is
dedicated to identifying and managing the risks involved in different kinds of strategies.

The learning objectives are:

● Detailed understanding Option Pricing Methodologies-Black-Scholes-Merton (BSM), factors which

impact Option Prices and Introduction to Option Greeks

● Understanding and forecasting volatility in options and discussing methodologies for analyzing options
trade, Volatility, Historical and Implied Volatility and its dynamics

● Variance premium, Hedging, Trading expiration

● Pre-trade expectations and finding mispriced volumes

● Trade planning and evaluation, Risk measures, an example that summarizes the volatility trading
process.

EPAT Project (Optional)

● Write your own working strategy starting from ideation, data analysis, strategy formulation,
back-testing, coding.

● Mentorship under a domain expert, practitioner.

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 6

● Project topics include, but not limited to, Pair trading strategies, Dispersion Trading, Machine
Learning, Skew Trading, Volatility Smile, Forward Volatility(You can check some of the past projects works at
https://www.quantinsti.com/category/project-work-epat​)

● Submission Requirements
a) Working Strategy Model
b) Project Report 2000-5000 words long

EPAT Final Exam

● We offer the world's first verified certification in algorithmic and quantitative trading through proctored
EPATcertification exams worldwide.

● The exams are conducted through the joint efforts of QuantInsti & our examination partner Prometric, one
of the leading test administrators globally.

Duration: 4 hours (Includes reaching 30 minutes before the exam start time and the break of up to 30 mins
between the two sections)

Format: Divided into two sections:

● EPAT Final Test contains MCQs (Multiple Choice Questions)

● EPAT Final Assignment contains Assignment type questions

● In case you finish the Quiz section, and there is spare time, the remaining time will be added to the
Assignment section

● You may take a break of up to 30 minutes (not included in the duration of either of the sections) between
the two sections. Please note that the second section will start automatically after 30 minutes of submitting
the first section.

Version 10.1.7 © Copyright QuantInsti Quantitative Learning Private Limited 7